Search Results for author:
Found 11 papers, 7 papers with code
UMBRAE: Unified Multimodal Decoding of Brain Signals
We address prevailing challenges of the brain-powered research, departing from the observation that the literature hardly recover accurate spatial information and require subject-specific models.
Blue noise for diffusion models
In this paper, we introduce a novel and general class of diffusion models taking correlated noise within and across images into account.
Zero-Shot Machine Unlearning at Scale via Lipschitz Regularization
The key challenge in unlearning is forgetting the necessary data in a timely manner, while preserving model performance.
DREAM: Visual Decoding from Reversing Human Visual System
In this work we present DREAM, an fMRI-to-image method for reconstructing viewed images from brain activities, grounded on fundamental knowledge of the human visual system.
Statistical shape representations for temporal registration of plant components in 3D
We present a landmark-free shape compression algorithm, which allows for the extraction of 3D shape features of leaves, characterises leaf shape and curvature efficiently in few parameters, and makes the association of individual leaves in feature space possible.
Path Guiding Using Spatio-Directional Mixture Models
In particular, we approximate incident radiance as an online-trained $5$D mixture that is accelerated by a $k$D-tree.
Shapley Value as Principled Metric for Structured Network Pruning
The usual pruning pipeline consists of ranking the network internal filters and activations with respect to their contributions to the network performance, removing the units with the lowest contribution, and fine-tuning the network to reduce the harm induced by pruning.
Differentiable Surface Splatting for Point-based Geometry Processing
We propose Differentiable Surface Splatting (DSS), a high-fidelity differentiable renderer for point clouds.
Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximation
The problem of explaining the behavior of deep neural networks has recently gained a lot of attention.
Active Mini-Batch Sampling using Repulsive Point Processes
We first show that the phenomenon of variance reduction by diversified sampling generalizes in particular to non-stationary point processes.
Towards better understanding of gradient-based attribution methods for Deep Neural Networks
Understanding the flow of information in Deep Neural Networks (DNNs) is a challenging problem that has gain increasing attention over the last few years.
